RobustBench-TC - Misleading Description: leaderboard

RobustBench-TC (2026) tests tool-calling models under deployment noise grounded in real tool-calling failures, using 199 single-turn samples drawn from BFCL, API-Bank, RoTBench, ToolAlpaca and ToolEyes and scored by deterministic rule-based parsers. This board is tool-call accuracy in percent under a misleading description on the correct tool and an attractive budget or fast suffix on a distractor; higher is better.

Metric: Tool-call accuracy (%) under the MisDesc perturbation (reward component: misleading description on GT; _Budget/_Fast suffix on distractor); RobustBench-TC samples drawn from BFCL V3 single-turn, API-Bank, RoTBench, ToolAlpaca and ToolEyes, each scored by its source benchmark's strict scorer after a format-tolerant tool-call parse, temperature 0 (DeepSeek-R1-Distill at 0.6), Qwen3-family models with thinking disabled; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 18 models tracked. Updated 7 Oct 2026.

Top models

#ModelSettingScoreOverall rank
1O4 Mini60.8#368
2DeepSeek R1 Distill Qwen 14B42.2#2771
3Qwen 3.5 9BNon-reasoning41.2#828
4MUA-RL-14B38.2#1658
5LoopTool-8B37.3#1473
6MUA-RL-32B35.3
7Qwen 3 32BNon-reasoning34.3#972
8Qwen 3 14BNon-reasoning33.3#1269
9LoopTool-32B33.3
10Qwen 3 8BNon-reasoning32.4#1873
11MUA-RL-8B32.4#1640
12ToolRL-Qwen2.5-1.5B26.5#2299
13Qwen 2.5 1.5B Instruct22.5#7470
14Qwen 2.5 3B Instruct20.6#5392
15TL-CodeLLaMA-219.6

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=robustbench-tc-misleading-description · How It Works · Data refreshed daily, snapshot 2026-11-21.